deepseek-ai / deepseek-ai/DeepEP
[Question] What's policy about apply ElasticBuffer for prefill?
Open
- Dominant language
- Cuda
- Stars
- 10.1k
- Forks
- 1.4k
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 2
Description
If very long input seqlen is need to be supported, how to init ElasticBuffer size for prefill? And how to alloc symm mem for the ElasticBuffer
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.